Establishment and Clinical Application of an Artificial Intelligence Diagnostic Platform for Identifying Rectal Cancer Tumor Budding

Abstract

Tumor budding is considered a sign of cancer cell activity and the first step of tumor metastasis. This study aimed to establish an automatic diagnostic platform for rectal cancer budding pathology by training a Faster region-based convolutional neural network (F-R-CNN) on the pathological images of rectal cancer budding. Postoperative pathological section images of 236 patients with rectal cancer from the Affiliated Hospital of Qingdao University, China, taken from January 2015 to January 2017 were used in the analysis. The tumor site was labeled in Label image software. The images of the learning set were trained using Faster R-CNN to establish an automatic diagnostic platform for tumor budding pathology analysis. The images of the test set were used to verify the learning outcome. The diagnostic platform was evaluated through the receiver operating characteristic (ROC) curve. Through training on pathological images of tumor budding, an automatic diagnostic platform for rectal cancer budding pathology was preliminarily established. The precision–recall curves were generated for the precision and recall of the nodule category in the training set. The area under the curve = 0.7414, which indicated that the training of Faster R-CNN was effective. The validation in the validation set yielded an area under the ROC curve of 0.88, indicating that the established artificial intelligence platform performed well at the pathological diagnosis of tumor budding. The established Faster R-CNN deep neural network platform for the pathological diagnosis of rectal cancer tumor budding can help pathologists make more efficient and accurate pathological diagnoses.

Prognostic significance of tumour budding in noncolorectal gastrointestinal tract and pancreatobiliary tract: a systematic review and meta‐analysis

“…Also, the increasing volume of digitized slide images has led to extensive research into applying artificial intelligence to automate the quantification of tumour budding. Several studies have explored algorithms for the automated detection and quantification of tumour budding, primarily focusing on CRC 80–83 . Moreover, research has expanded to include invasive bladder cancer and oral squamous cell carcinoma 84,85 .…”

“…Several studies have explored algorithms for the automated detection and quantification of tumour budding, primarily focusing on CRC. [80][81][82][83] Moreover, research has expanded to include invasive bladder cancer and oral squamous cell carcinoma. 84,85 The quantification of tumour budding is labor-intensive, with persistent concerns about inter/intraobserver variability.…”

Quantification of the Immune Content in Neuroblastoma: Deep Learning and Topological Data Analysis in Digital Pathology

“…The former set of architectures is mainly aimed at quick object detection, with fast R-CNN [57] as the first implementation, followed by its improved version, faster R-CNN [58]. These models still work as building blocks for recent solutions in DP, as in [59][60][61]. The latter family of models stem from the prototypal structure mask R-CNN [62,63], obtained by optimizing the faster R-CNN for pixel-level segmentation tasks.…”

“…In the top panel, the ID is plotted for each inner block for all the training epochs. In (panel b), ID is plotted for the first three epochs (1,7,13) and for the last epoch (60), which corresponds to the highest peak of the encoder. During the central epochs (panel c) ID values of the encoder are stable, while the ID values of the decoder still show some variability; in particular (panel d) a ID peak on the third block.…”

A systematic review on application of deep learning in digestive system image processing

“…Standardized images have the advantage of removing stained samples, but retrospective studies can also lead to selective bias, and different staining conditions can affect CAD diagnoses. There have been retrospective studies on DL in the pathological diagnosis and prognosis analysis of Helicobacter pylori gastritis [ 78 ], rectal cancer [ 79 ], pancreatic tumors [ 80 ], gastrointestinal, and endocrine tumors [ 81 ]. Prospective, multi-center, and large-scale trials have also begun to verify these algorithms’ usability [ 82 ].…”