Cloud-Based AutoML Classification of Malignant and Non-malignant Colorectal Findings on Abdominal Computed Tomography: A Proof-of-Concept Study.
7 affiliations
- 1Internal Medicine, California Northstate University College of Medicine, Elk Grove, USA.
- 2Osteopathic Medicine, Touro University California, Vallejo, USA.
- 3Internal Medicine, California Health Sciences University, Fresno, USA.
- 4Medicine, California University of Science and Medicine, Colton, USA.
- 5Medicine, The University of Oklahoma, Norman, USA.
- 6Medicine, University of California, Los Angeles, Los Angeles, USA.
- 7Internal Medicine, East Tennessee State University Quillen College of Medicine, Johnson City, USA.
Abstract
Colorectal cancer (CRC) is a major cause of cancer-related morbidity and mortality worldwide, and computed tomography (CT) plays an important role in its clinical evaluation and staging. However, CT interpretation may be influenced by lesion conspicuity, acquisition characteristics, and reader experience. Artificial intelligence (AI)-based image analysis may provide a reproducible adjunct to conventional radiologic assessment. This study evaluated a cloud-based automated machine-learning image-classification model for distinguishing malignant from non-malignant abdominal CT images. Images were obtained from the publicly available ColonCancerCT-2025 dataset, which contains CT imaging and clinical information from 40 patients, including 12 malignant and 28 non-malignant cases. For the present analysis, 3,827 CT images were included. The images were divided into training, validation, and test sets in an approximately 80:10:10 ratio, comprising 3,062 training images, 383 validation images, and 382 test images. Patient-level separation among these partitions could not be confirmed from the retained study workflow. A single-label binary image-classification model was developed using Google Cloud AutoML (Google LLC, Mountain View, CA, USA). Model performance was evaluated using average precision, precision, recall, precision-recall analysis, confidence-threshold behavior, and a normalized confusion matrix. A confidence threshold of 0.50 was used for the primary performance assessment. At this threshold, the classifier achieved an overall average precision of 0.998, with precision and recall of approximately 99%. Class-specific average precision was 0.998 for malignant images and 0.999 for non-malignant images. The normalized confusion matrix demonstrated correct classification of 97% of malignant images and 100% of non-malignant images. Representative correctly classified images received prediction probabilities of 0.947 for the malignant class and 0.960 for the non-malignant class. These findings demonstrate the feasibility of cloud-based automated image classification for colorectal CT analysis; however, the limited number of patients, lack of confirmed patient-level separation between dataset partitions, absence of independent external testing, and image-level rather than examination-level evaluation substantially limit conclusions regarding clinical generalizability. Larger patient-level, multi-institutional studies are required before such a model can be considered for clinical decision support.
Related
- The Spectrum of Eyelid Lesions: Histopathologic Classification of Benign, Malignant, and Non-Neoplastic Findings
- Long-term outcomes of splanchnic radiofrequency ablation for control of chronic abdominal visceral, non-malignant pain
- Cough-induced rectus sheath hematoma in an adolescent without external abdominal findings: a case report
- FBXO17 regulates the malignant progression of colorectal cancer via the Wnt/β-catenin pathway
- External Root Resorption: Unique Cone Beam Computed Tomography Findings of a Rare Radiographic Entity
BibTeX
@article{bachir2026cloudbased,
title = {{Cloud-Based AutoML Classification of Malignant and Non-malignant Colorectal Findings on Abdominal Computed Tomography: A Proof-of-Concept Study.}},
author = {Mark A Bachir and Neel Nawathey and Alexander S Bachir and Akshay J Reddy and Jacob Webster and Simran Gill and Rakesh Patel},
journal = {Cureus},
year = {2026},
month = sep,
doi = {10.7759/cureus.116802},
url = {https://europepmc.org/article/MED/42927376},
note = {CC BY},
}
RIS
TY - JOUR
TI - Cloud-Based AutoML Classification of Malignant and Non-malignant Colorectal Findings on Abdominal Computed Tomography: A Proof-of-Concept Study.
AU - Mark A Bachir
AU - Neel Nawathey
AU - Alexander S Bachir
AU - Akshay J Reddy
AU - Jacob Webster
AU - Simran Gill
AU - Rakesh Patel
PY - 2026
DA - 2026/09/23
JO - Cureus
DO - 10.7759/cureus.116802
UR - https://europepmc.org/article/MED/42927376
AB - Colorectal cancer (CRC) is a major cause of cancer-related morbidity and mortality worldwide, and computed tomography (CT) plays an important role in its clinical evaluation and staging. However, CT interpretation may be influenced by lesion conspicuity, acquisition characteristics, and reader experience. Artificial intelligence (AI)-based image analysis may provide a reproducible adjunct to conventional radiologic assessment. This study evaluated a cloud-based automated machine-learning image-classification model for distinguishing malignant from non-malignant abdominal CT images. Images were obtained from the publicly available ColonCancerCT-2025 dataset, which contains CT imaging and clinical information from 40 patients, including 12 malignant and 28 non-malignant cases. For the present analysis, 3,827 CT images were included. The images were divided into training, validation, and test sets in an approximately 80:10:10 ratio, comprising 3,062 training images, 383 validation images, and 382 test images. Patient-level separation among these partitions could not be confirmed from the retained study workflow. A single-label binary image-classification model was developed using Google Cloud AutoML (Google LLC, Mountain View, CA, USA). Model performance was evaluated using average precision, precision, recall, precision-recall analysis, confidence-threshold behavior, and a normalized confusion matrix. A confidence threshold of 0.50 was used for the primary performance assessment. At this threshold, the classifier achieved an overall average precision of 0.998, with precision and recall of approximately 99%. Class-specific average precision was 0.998 for malignant images and 0.999 for non-malignant images. The normalized confusion matrix demonstrated correct classification of 97% of malignant images and 100% of non-malignant images. Representative correctly classified images received prediction probabilities of 0.947 for the malignant class and 0.960 for the non-malignant class. These findings demonstrate the feasibility of cloud-based automated image classification for colorectal CT analysis; however, the limited number of patients, lack of confirmed patient-level separation between dataset partitions, absence of independent external testing, and image-level rather than examination-level evaluation substantially limit conclusions regarding clinical generalizability. Larger patient-level, multi-institutional studies are required before such a model can be considered for clinical decision support.
SN - 2168-8184
ER -