Submit to Special Issue Submit Abstract to Special Issue Review for Cancers Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging

Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Therapy".

Deadline for manuscript submissions: 1 July 2025 | Viewed by 5750

Share This Special Issue

Special Issue Editor

Dr. Fereshteh Yousefirizi

E-Mail Website
Guest Editor

Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC V5Z 1L3, Canada
Interests: physician-in-the-loop; PET/CT; AI; foundation model; generalist model; tumor segmentation; outcome prediction; whole-body PET; cancers
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue aims to bridge the gap between AI algorithms developed in academia and the practical needs of clinical oncological PET/CT imaging. It addresses challenges such as model generalizability, economic feasibility, and regulatory constraints that limit the adoption of AI-based solutions in clinical settings. Additionally, it highlights the struggle of AI-based techniques developed in academic research labs to gain clinical trust compared to industrial solutions, which benefit from extensive datasets and clinical approvals.

AI promises significant advancements in diagnosis, treatment assessment, and planning, particularly in oncologic PET/CT imaging. However, challenges such as model generalizability, economic feasibility, and regulatory hurdles significantly hinder the widespread adoption of AI-based solutions in clinical settings. Techniques introduced by research labs often struggle to gain clinical trust compared to industrial solutions, which benefit from extensive datasets and clinical approvals. Moreover, the lack of agreed-upon problem statements and effective collaboration tools has impeded the integration of academic advancements into clinical practice.

This Special Issue seeks contributions from technical and clinical researchers to share their solutions and results within this framework. We are particularly interested in foundational and generalist medical AI models capable of performing diverse tasks using minimally labeled data through self-supervised and active learning. These models should be capable of interpreting various medical modalities, including imaging, electronic health records, lab results, genomics, graphs, and medical text, by leveraging large, diverse datasets. Specialists such as oncologists, nuclear medicine experts, and medical physicists will guide these models using specific prompts, ensuring that responses are informed by their expertise.

Dr. Fereshteh Yousefirizi
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Cancers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

physician-in-the-loop
PET/CT
AI
foundation model
generalist model
tumor segmentation
outcome prediction
whole-body PET
cancers

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (7 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review, Other

15 pages, 2843 KiB

Open AccessArticle

Improving the Precision of Deep-Learning-Based Head and Neck Target Auto-Segmentation by Leveraging Radiology Reports Using a Large Language Model

by Libing Zhu, Jean-Claude M. Rwigema, Xue Feng, Bilaal Ansari, Jingwei Duan, Yi Rong and Quan Chen

Cancers 2025, 17(12), 1935; https://doi.org/10.3390/cancers17121935 - 10 Jun 2025

Abstract

Background/Objectives: The accurate delineation of primary tumors (GTVp) and metastatic lymph nodes (GTVn) in head and neck (HN) cancers is essential for effective radiation treatment planning, yet remains a challenging and laborious task. This study aims to develop a deep-learning-based auto-segmentation (DLAS) model trained on external datasets with false-positive elimination using clinical diagnosis reports. Methods: The DLAS model was trained on a multi-institutional public dataset with 882 cases. Forty-four institutional cases were randomly selected as the external testing dataset. DLAS-generated GTVp and GTVn were validated against clinical diagnosis reports to identify false-positive and false-negative segmentation errors using two large language models: ChatGPT-4 and Llama-3. False-positive ruling out was conducted by matching the centroids of AI-generated contours with the slice locations or anatomical regions described in the reports. Performance was evaluated using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), and tumor detection precision. Results: ChatGPT-4 outperformed Llama-3 in accurately extracting tumor locations from the diagnostic reports. False-positive contours were identified in 15 out of 44 cases. The DSC_mean of the DLAS contours for GTVp and GTVn increased from 0.68 to 0.75 and from 0.69 to 0.75, respectively, after the ruling-out process. Notably, the average HD95 value for GTVn decreased from 18.81 mm to 5.2 mm. Post ruling out, the model achieved 100% precision for GTVp and GTVn when compared with the results of physician-determined contours. Conclusions: The false-positive ruling-out approach based on diagnostic reports effectively enhances the precision of DLAS in the HN region. The model accurately identifies the tumor location and detects all false-negative errors. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

19 pages, 1817 KiB

Open AccessArticle

Radiomic Features Prognosticate Treatment Response in CAR-T Cell Therapy

by Yoganand Balagurunathan, Jung W. Choi, Zachary Thompson, Michael Jain and Frederick L. Locke

Cancers 2025, 17(11), 1832; https://doi.org/10.3390/cancers17111832 - 30 May 2025

Viewed by 324

Abstract

Background: Diffuse large B-cell lymphomas (DLBCLs) are the most common, aggressive disease form that accounts for 30% of all lymphoma cases. Identifying patients who will respond to these advanced cell-based therapies is an unaddressed challenge. Methods: We propose to develop a radiomics- (quantitative image metric) based signature on the patients’ imaging scans (positron emission tomography/computed tomography, PET/CT) and use these metrics to prognosticate response to axi-cel (axicabtagene ciloleucel), autologous CD19 chimeric antigen receptor (CAR) T-cell (CAR-T) therapy. We curated a cohort of 155 patients with relapsed/refractory (R/R) DLBCL who were treated with axi-cel. Using their baseline image scan (PET/CT), the largest lesions related to nodal/extra-nodal disease were identified and characterized using imaging metrics (radiomics). We used principal component (PC) analysis to reduce the dimensionality of these features across the functional categories (size, shape, and texture). We evaluated the prognostic ability of radiomic-based PC to treatment response (1-year), measured by overall survival (OS) and progression-free survival (PFS). Results: We found that radiomic PC was prognostic of overall survival (Shape-PC, q < 0.013/0.0108, Size-PC, q < 0.003/0.0088), in CT/PET, respectively. In comparison, the metabolic tumor volume (MTV) was prognostic (q < 0.0002/0.0007). The radiomic PCs across the functional categories showed moderate to weak correlation with MTV, Spearman’s ρ of 0.44/0.35/0.27, and 0.45/0.36/0.55 for Size/Shape/Texture-PC1 obtained on PET and CT, respectively. Conclusions: We found radiomic PC based on size and shape metrics that are able to prognosticate treatment response to CAR-T therapy. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

38 pages, 11406 KiB

Open AccessArticle

Detection of Local Prostate Cancer Recurrence from PET/CT Scans Using Deep Learning

by Marko Korb, Hülya Efetürk, Tim Jedamzik, Philipp E. Hartrampf, Aleksander Kosmala, Sebastian E. Serfling, Robin Dirk, Kerstin Michalski, Andreas K. Buck, Rudolf A. Werner, Wiebke Schlötelburg and Markus J. Ankenbrand

Cancers 2025, 17(9), 1575; https://doi.org/10.3390/cancers17091575 - 6 May 2025

Viewed by 427

Abstract

Background: Prostate cancer (PC) is a leading cause of cancer-related deaths in men worldwide. PSMA-directed positron emission tomography (PET) has shown promising results in detecting recurrent PC and metastasis, improving the accuracy of diagnosis and treatment planning. To evaluate an artificial intelligence (AI) model based on [¹⁸F]-prostate specific membrane antigen (PSMA)-1007 PET datasets for the detection of local recurrence in patients with prostate cancer. Methods: We retrospectively analyzed 1404 [¹⁸F]-PSMA-1007 PET/CTs from patients with histologically confirmed prostate cancer. Artificial neural networks were trained to recognize the presence of local recurrence based on the PET data. First, the hyperparameters were optimized for an initial model (model A). Subsequently, the bladder was localized using an already published model and a model (model B) was trained only on a 20 cm cube around the bladder. Finally, two separate models were trained on the same section depending on the prostatectomy status (model C (post-prostatectomy) and model D (non-operated)). Results: Model A achieved an accuracy of 56% on the validation data. By restricting the region to the area around the bladder, Model B achieved a validation accuracy of 71%. When validating the specialized models according to prostatectomy status, model C achieved an accuracy of 77% and model D an accuracy of 77%. All models achieved accuracies of almost 100% on the training data, indicating overfitting. Conclusions: For the presented task, 1404 examinations were insufficient to reach an accuracy of over 90% even when employing data augmentation, including additional metadata and performing automated hyperparameter optimization. The low F1-score and AUC values indicate that none of the presented models produce reliable results. However, we will facilitate future research and the development of better models by openly sharing our source code and all pre-trained models for transfer learning. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

12 pages, 3714 KiB

Open AccessArticle

A Machine Learning-Based Radiomics Model for the Differential Diagnosis of Benign and Malignant Thyroid Nodules in F-18 FDG PET/CT: External Validation in the Different Scanner

by Junchae Lee, Jinny Lee and Bong-Il Song

Cancers 2025, 17(2), 331; https://doi.org/10.3390/cancers17020331 - 20 Jan 2025

Viewed by 920

Abstract

Background/Objectives: Accurate diagnosis is essential to avoid unnecessary procedures for thyroid incidentalomas (TIs). Advances in radiomics and machine learning applied to medical imaging offer promise for assessing thyroid nodules. This study utilized radiomics analysis on F-18 FDG PET/CT to improve preoperative differential diagnosis of TIs. Methods: A total of 152 patient cases were retrospectively analyzed and split into training and validation sets (7:3) using stratification and randomization. Results: The least absolute shrinkage and selection operator (LASSO) algorithm identified nine radiomics features from 960 candidates to construct a radiomics signature predictive of malignancy. Performance of the radiomics score was evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC). In the training set, the radiomics score achieved an AUC of 0.794 (95% CI: 0.703–0.885, p < 0.001). Validation was performed on internal and external datasets, yielding AUCs of 0.702 (95% CI: 0.547–0.858, p = 0.011) and 0.668 (95% CI: 0.500–0.838, p = 0.043), respectively. Conclusions: These results demonstrate that the selected nine radiomics features effectively differentiate malignant thyroid nodules. Overall, the radiomics model shows potential as a valuable predictive tool for thyroid cancer in patients with TIs, supporting improved preoperative decision-making. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

16 pages, 2726 KiB

Open AccessArticle

The Challenge of External Generalisability: Insights from the Bicentric Validation of a [⁶⁸Ga]Ga-PSMA-11 PET Based Radiomics Signature for Primary Prostate Cancer Characterisation Using Histopathology as Reference

by Samuele Ghezzo, Praveen Gurunath Bharathi, Heying Duan, Paola Mapelli, Philipp Sorgo, Guido Alejandro Davidzon, Carolina Bezzi, Benjamin Inbeh Chung, Ana Maria Samanes Gajate, Alan Eih Chih Thong, Tommaso Russo, Giorgio Brembilla, Andreas Markus Loening, Pejman Ghanouni, Anna Grattagliano, Alberto Briganti, Francesco De Cobelli, Geoffrey Sonn, Arturo Chiti, Andrei Iagaru, Farshad Moradi and Maria Picchio Show full author list Hide full author list

Cancers 2024, 16(23), 4103; https://doi.org/10.3390/cancers16234103 - 7 Dec 2024

Cited by 1 | Viewed by 1259

Abstract

Background: PSMA PET radiomics is a promising tool for primary prostate cancer (PCa) characterisation. However, small single-centre studies and lack of external validation hinder definitive conclusions on the potential of PSMA PET radiomics in the initial workup of PCa. We aimed to validate a radiomics signature in a larger internal cohort and in an external cohort from a separate centre. Methods: One hundred and twenty-seven PCa patients were retrospectively enrolled across two independent hospitals. The first centre (IRCCS San Raffaele Scientific Institute, Centre 1) contributed 62 [⁶⁸Ga]Ga-PSMA-11 PET scans, 20 patients classified as low-grade (ISUP grade < 4), and 42 as high-grade (ISUP grade ≥ 4). The second centre (Stanford University Hospital, Centre 2) provided 65 [⁶⁸Ga]Ga-PSMA-11 PET scans, and 49 low-grade and 16 high-grade patients. A radiomics model previously generated in Centre 1 was tested on the two cohorts separately and afterward on the entire dataset. Then, we evaluated whether the radiomics features selected in the previous investigation could generalise to new data. Several machine learning (ML) models underwent training and testing using 100-fold Monte Carlo cross-validation, independently at both Centre 1 and Centre 2, with a 70–30% train–test split. Additionally, models were trained in one centre and tested in the other, and vice versa. Furthermore, data from both centres were combined for training and testing using Monte Carlo cross-validation. Finally, a new radiomics signature built on this bicentric dataset was proposed. Several performance metrics were computed. Results: The previously generated radiomics signature resulted in an area under the receiver operating characteristic curve (AUC) of 80.4% when tested on Centre 1, while it generalised poorly to Centre 2, where it reached an AUC of 62.7%. When the whole cohort was considered, AUC was 72.5%. Similarly, new ML models trained on the previously selected features yielded, at best, an AUC of 80.9% for Centre 1 and performed at chance for Centre 2 (AUC of 49.3%). A new signature built on this bicentric dataset reached, at best, an average AUC of 91.4% in the test set. Conclusions: The satisfying performance of radiomics models when used in the original development settings, paired with the poor performance otherwise observed, emphasises the need to consider centre-specific factors and dataset characteristics when developing radiomics models. Combining radiomics datasets is a viable strategy to reduce such centre-specific biases, but external validation is still needed. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

Review

Jump to: Research, Other

26 pages, 4445 KiB

Open AccessReview

Effectiveness of Artificial Intelligence Models in Predicting Lung Cancer Recurrence: A Gene Biomarker-Driven Review

by Niloufar Pourakbar, Alireza Motamedi, Mahta Pashapour, Mohammad Emad Sharifi, Seyedemad Seyedgholami Sharabiani, Asra Fazlollahi, Hamid Abdollahi, Arman Rahmim and Sahar Rezaei

Cancers 2025, 17(11), 1892; https://doi.org/10.3390/cancers17111892 - 5 Jun 2025

Viewed by 275

Abstract

Background/Objectives: Lung cancer recurrence, particularly in NSCLC, remains a major challenge, with 30–70% of patients relapsing post-treatment. Traditional predictors like TNM staging and histopathology fail to account for tumor heterogeneity and immune dynamics. This review evaluates AI models integrating gene biomarkers (TP53, KRAS, FOXP3, PD-L1, and CD8) to enhance the recurrence prediction and improve the personalized risk stratification. Methods: Following the PRISMA guidelines, we systematically reviewed AI-driven recurrence prediction models for lung cancer, focusing on genomic biomarkers. Studies were selected based on predefined criteria, emphasizing AI/ML approaches integrating gene expression, radiomics, and clinical data. Data extraction covered the study design, AI algorithms (e.g., neural networks, SVM, and gradient boosting), performance metrics (AUC and sensitivity), and clinical applicability. Two reviewers independently screened and assessed studies to ensure accuracy and minimize bias. Results: A literature analysis of 18 studies (2019–2024) from 14 countries, covering 4861 NSCLC and small cell lung cancer patients, showed that AI models outperformed conventional methods. AI achieved AUCs of 0.73–0.92 compared to 0.61 for TNM staging. Multi-modal approaches integrating gene expression (PDIA3 and MYH11), radiomics, and clinical data improved accuracy, with SVM-based models reaching a 92% AUC. Key predictors included immune-related signatures (e.g., tumor-infiltrating NK cells and PD-L1 expression) and pathway alterations (NF-κB and JAK-STAT). However, small cohorts (41–1348 patients), data heterogeneity, and limited external validation remained challenges. Conclusions: AI-driven models hold potential for recurrence prediction and guiding adjuvant therapies in high-risk NSCLC patients. Expanding multi-institutional datasets, standardizing validation, and improving clinical integration are crucial for real-world adoption. Optimizing biomarker panels and using AI trustworthily and ethically could enhance precision oncology, enabling early, tailored interventions to reduce mortality. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Figure 1

Other

Jump to: Research, Review

24 pages, 3097 KiB

Open AccessSystematic Review

A Systematic Review of the Applications of Deep Learning for the Interpretation of Positron Emission Tomography Images of Patients with Lymphoma

by Theofilos Kanavos, Effrosyni Birbas and Theodoros P. Zanos

Cancers 2025, 17(1), 69; https://doi.org/10.3390/cancers17010069 - 29 Dec 2024

Viewed by 1548

Abstract

Background: Positron emission tomography (PET) is a valuable tool for the assessment of lymphoma, while artificial intelligence (AI) holds promise as a reliable resource for the analysis of medical images. In this context, we systematically reviewed the applications of deep learning (DL) for the interpretation of lymphoma PET images. Methods: We searched PubMed until 11 September 2024 for studies developing DL models for the evaluation of PET images of patients with lymphoma. The risk of bias and applicability concerns were assessed using the prediction model risk of bias assessment tool (PROBAST). The articles included were categorized and presented based on the task performed by the proposed models. Our study was registered with the international prospective register of systematic reviews, PROSPERO, as CRD42024600026. Results: From 71 papers initially retrieved, 21 studies with a total of 9402 participants were ultimately included in our review. The proposed models achieved a promising performance in diverse medical tasks, namely, the detection and histological classification of lesions, the differential diagnosis of lymphoma from other conditions, the quantification of metabolic tumor volume, and the prediction of treatment response and survival with areas under the curve, F1-scores, and R² values of up to 0.963, 87.49%, and 0.94, respectively. Discussion: The primary limitations of several studies were the small number of participants and the absence of external validation. In conclusion, the interpretation of lymphoma PET images can reliably be aided by DL models, which are not designed to replace physicians but to assist them in managing large volumes of scans through rapid and accurate calculations, alleviate their workload, and provide them with decision support tools for precise care and improved outcomes. Full article

(This article belongs to the Special Issue Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging)

► Show Figures

Journal Menu

Journal Browser

Bridging the Gap: Integrating AI into Clinical Practice for Oncological PET/CT Imaging

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (7 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI