Projects per year
This paper investigates the visual classification of the 10 skin lesions most commonly encountered in a clinical setting (including melanoma (MEL) and melanocytic nevi (ML)), unlike the majority of previous research that focuses solely on melanoma versus melanocytic nevi classification. Two families of architectures are explored: 1) semilearned hierarchical classifiers and 2) deep net classifiers. Although many applications have benefited by switching to a deep net architecture, here there is little accuracy benefit: hierarchical KNN classifier 78.1%, flat deep net 78.7% and refined hierarchical deep net 80.1% (all 5 fold cross-validated). The classifiers have comparable or higher accuracy than the five previous research results that have used the Edinburgh DERMOFIT 10 lesion class dataset. More importantly, from a clinical perspective, the proposed hierarchical KNN approach produces: 1) 99.5% separation of melanoma from melanocytic nevi (76 MEL & 331 ML samples), 2) 100% separation of melanoma from seborrheic keratosis (SK) (76 MEL & 256 SK samples), and 3) 90.6% separation of basal cell carcinoma (BCC) plus squamous cell carcinoma (SCC) from seborrheic keratosis (SK) (327 BCC/SCC & 256 SK samples). Moreover, combining classes BCC/SCC & ML/SK to give a modified 8 class hierarchical KNN classifier gives a considerably improved 87.1% accuracy. On the other hand, the deepnet binary cancer/non-cancer classifier had better performance (0.913) than the KNN classifier (0.874). In conclusion, there is not much difference between the two familes of approaches, and that performance is approaching clinically useful rates.
|Title of host publication||Medical Image Understanding and Analysis|
|Subtitle of host publication||23rd Conference, MIUA 2019, Liverpool, UK, July 24-26, 2019, Proceedings|
|Number of pages||12|
|Publication status||Published - 24 Jan 2020|
|Event||23rd Conference on Medical Image Understanding and Analysis - Liverpool, United Kingdom|
Duration: 24 Jul 2019 → 26 Jul 2019
|Name||Communications in Computer and Information Science (CCIS)|
|Conference||23rd Conference on Medical Image Understanding and Analysis|
|Abbreviated title||MIUA 2019|
|Period||24/07/19 → 26/07/19|
- Skin cancer
- RGB image analysis
FingerprintDive into the research topics of 'Classification of Ten Skin Lesion Classes: Hierarchical KNN versus Deep Net'. Together they form a unique fingerprint.
- 1 Finished
Fisher, B. & Rees, J.
15/09/08 → 14/09/11