Confident texture-based laryngeal tissue classification for early stage diagnosis support

Abstract

Early stage diagnosis of laryngeal squamous cell carcinoma (SCC) is of primary importance for lowering patient mortality or after treatment morbidity. Despite the challenges in diagnosis reported in the clinical literature, few efforts have been invested in computer-assisted diagnosis. The objective of this paper is to investigate the use of texture-based machine-learning algorithms for early stage cancerous laryngeal tissue classification. To estimate the classification reliability, a measure of confidence is also exploited. From the endoscopic videos of 33 patients affected by SCC, a well-balanced dataset of 1320 patches, relative to four laryngeal tissue classes, was extracted. With the best performing feature, the achieved median classification recall was 93% [interquartile range [Formula: see text]]. When excluding low-confidence patches, the achieved median recall was increased to 98% ([Formula: see text]), proving the high reliability of the proposed approach. This research represents an important advancement in the state-of-the-art computer-assisted laryngeal diagnosis, and the results are a promising step toward a helpful endoscope-integrated processing system to support early stage diagnosis.

Computer-assisted liver graft steatosis assessment via learning-based texture analysis

“…Thus, as future work, we aim at enlarging the training dataset, exploiting also different RGB-camera devices, to validate the experimental analysis presented here. We also aim at investigating if including a measure of confidence on classification, such as in [22,23], could help further improving classification reliability.…”

“…As in [22], and since texture is a local image-property, we decided to compute textural features from image patches, which were extracted as explained in Sec. 2.3.…”

“…Inspired by these recent and promising studies, and in particular by our previous research focused on the laryngeal district [22], in this paper we aim at investigating if liver-texture analysis from RGB images acquired with smartphones in the operating room (OR) coupled with machine learning can provide reliable results, to be used as support for LT decision. This paper is organized as follows: Sec.…”

“…The histogram of local binary patterns (LBP) is exploited for tissue classification in several anatomical districts, such as abdomen, larynx, gastro-intestinal tract (e.g. [15,32,23,22,16]). Gray-level co-occurrence matrix (GLCM)-based features have also been exploited for tissue classification.…”

Surgical data science, an emerging field of medicine

“…After the procedure, the collected data can be used for statistical analysis, providing information on surgical performance. CAD: Computer-Aided Design CAM: Computer-Aided Manufacturing TQM: Total Quality Management applications have been developed: for organ [26] and tissue classification [27], [28], as well as for tool recognition [29]. Recently several surgical phase detection algorithms have been presented using Random Forests (RF), Hidden Markov Models (HMM) and deep neural networks [30], [31], [32].…”